The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
최근에는 GNSS(Global Navigation Satellite System) 측위가 다양한 애플리케이션(예: 자동차 내비게이션 시스템, 스마트폰 지도 애플리케이션, 자율주행)에 널리 사용되고 있습니다. GNSS 포지셔닝에서는 관측된 위성 신호로부터 좌표가 계산됩니다. 관측된 신호에는 다양한 오류가 포함되어 있으므로 계산된 좌표에도 일부 오류가 있습니다. 이중차분법은 관찰된 신호의 오류를 줄이기 위해 널리 사용되는 아이디어 중 하나입니다. 이중차분을 통해 관찰된 신호에서 다양한 종류의 오류를 제거할 수 있지만 일부 오류는 여전히 남아 있습니다(예: 다중 경로 오류). 본 논문에서는 남은 오차를 “이중차분오차(DDE)”로 정의하고, 머신러닝을 활용하여 DDE를 추정하는 방법을 제안한다. 또한 추정된 DDE를 피드백하여 DGNSS 포지셔닝을 개선하려고 시도합니다. GNSS에 머신러닝을 적용한 이전 연구에서는 신호가 LOS(Line Of Sight)인지 NLOS(Non Line Of Sight)인지 분류하는 데 중점을 두었으며, 우리가 아는 한 오류량 자체를 추정하려는 연구는 없습니다. 또한, 이전 연구에서는 데이터 세트가 동일한 도시의 몇몇 위치에서만 기록된다는 한계가 있었습니다. 이는 이러한 연구들이 주로 차량의 측위 정확도를 향상시키는 것을 목표로 하고 있으며, 차량을 이용하여 많은 양의 데이터를 수집하는 데 비용이 많이 들기 때문입니다. 이 문제를 피하기 위해 이 연구에서는 공개적으로 사용 가능한 엄청난 양의 고정 점 데이터를 훈련에 사용합니다. 실험을 통해 제안하는 방법이 DGNSS 측위 오차를 줄일 수 있음을 확인하였다. 비록 DDE 추정기가 정지점 데이터에 대해서만 학습되었음에도 불구하고 제안된 방법은 정지점뿐만 아니라 이동 로버에서도 DGNSS 측위 정확도를 향상시켰다. 또한 이전(탐지 및 제거) 접근 방식과 비교하여 DDE 피드백 접근 방식의 효율성을 확인했습니다.
Hirotaka KATO
Meijo University
Junichi MEGURO
Meijo University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Hirotaka KATO, Junichi MEGURO, "Improvement of Differential-GNSS Positioning by Estimating Code Double-Difference-Error Using Machine Learning" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 12, pp. 2069-2077, December 2023, doi: 10.1587/transinf.2023EDP7015.
Abstract: Recently, Global navigation satellite system (GNSS) positioning has been widely used in various applications (e.g. car navigation system, smartphone map application, autonomous driving). In GNSS positioning, coordinates are calculated from observed satellite signals. The observed signals contain various errors, so the calculated coordinates also have some errors. Double-difference is one of the widely used ideas to reduce the errors of the observed signals. Although double-difference can remove many kinds of errors from the observed signals, some errors still remain (e.g. multipath error). In this paper, we define the remaining error as “double-difference-error (DDE)” and propose a method for estimating DDE using machine learning. In addition, we attempt to improve DGNSS positioning by feeding back the estimated DDE. Previous research applying machine learning to GNSS has focused on classifying whether the signal is LOS (Line Of Sight) or NLOS (Non Line Of Sight), and there is no study that attempts to estimate the amount of error itself as far as we know. Furthermore, previous studies had the limitation that their dataset was recorded at only a few locations in the same city. This is because these studies are mainly aimed at improving the positioning accuracy of vehicles, and collecting large amounts of data using vehicles is costly. To avoid this problem, in this research, we use a huge amount of openly available stationary point data for training. Through the experiments, we confirmed that the proposed method can reduce the DGNSS positioning error. Even though the DDE estimator was trained only on stationary point data, the proposed method improved the DGNSS positioning accuracy not only with stationary point but also with mobile rover. In addition, by comparing with the previous (detect and remove) approach, we confirmed the effectiveness of the DDE feedback approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7015/_p
부
@ARTICLE{e106-d_12_2069,
author={Hirotaka KATO, Junichi MEGURO, },
journal={IEICE TRANSACTIONS on Information},
title={Improvement of Differential-GNSS Positioning by Estimating Code Double-Difference-Error Using Machine Learning},
year={2023},
volume={E106-D},
number={12},
pages={2069-2077},
abstract={Recently, Global navigation satellite system (GNSS) positioning has been widely used in various applications (e.g. car navigation system, smartphone map application, autonomous driving). In GNSS positioning, coordinates are calculated from observed satellite signals. The observed signals contain various errors, so the calculated coordinates also have some errors. Double-difference is one of the widely used ideas to reduce the errors of the observed signals. Although double-difference can remove many kinds of errors from the observed signals, some errors still remain (e.g. multipath error). In this paper, we define the remaining error as “double-difference-error (DDE)” and propose a method for estimating DDE using machine learning. In addition, we attempt to improve DGNSS positioning by feeding back the estimated DDE. Previous research applying machine learning to GNSS has focused on classifying whether the signal is LOS (Line Of Sight) or NLOS (Non Line Of Sight), and there is no study that attempts to estimate the amount of error itself as far as we know. Furthermore, previous studies had the limitation that their dataset was recorded at only a few locations in the same city. This is because these studies are mainly aimed at improving the positioning accuracy of vehicles, and collecting large amounts of data using vehicles is costly. To avoid this problem, in this research, we use a huge amount of openly available stationary point data for training. Through the experiments, we confirmed that the proposed method can reduce the DGNSS positioning error. Even though the DDE estimator was trained only on stationary point data, the proposed method improved the DGNSS positioning accuracy not only with stationary point but also with mobile rover. In addition, by comparing with the previous (detect and remove) approach, we confirmed the effectiveness of the DDE feedback approach.},
keywords={},
doi={10.1587/transinf.2023EDP7015},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - Improvement of Differential-GNSS Positioning by Estimating Code Double-Difference-Error Using Machine Learning
T2 - IEICE TRANSACTIONS on Information
SP - 2069
EP - 2077
AU - Hirotaka KATO
AU - Junichi MEGURO
PY - 2023
DO - 10.1587/transinf.2023EDP7015
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2023
AB - Recently, Global navigation satellite system (GNSS) positioning has been widely used in various applications (e.g. car navigation system, smartphone map application, autonomous driving). In GNSS positioning, coordinates are calculated from observed satellite signals. The observed signals contain various errors, so the calculated coordinates also have some errors. Double-difference is one of the widely used ideas to reduce the errors of the observed signals. Although double-difference can remove many kinds of errors from the observed signals, some errors still remain (e.g. multipath error). In this paper, we define the remaining error as “double-difference-error (DDE)” and propose a method for estimating DDE using machine learning. In addition, we attempt to improve DGNSS positioning by feeding back the estimated DDE. Previous research applying machine learning to GNSS has focused on classifying whether the signal is LOS (Line Of Sight) or NLOS (Non Line Of Sight), and there is no study that attempts to estimate the amount of error itself as far as we know. Furthermore, previous studies had the limitation that their dataset was recorded at only a few locations in the same city. This is because these studies are mainly aimed at improving the positioning accuracy of vehicles, and collecting large amounts of data using vehicles is costly. To avoid this problem, in this research, we use a huge amount of openly available stationary point data for training. Through the experiments, we confirmed that the proposed method can reduce the DGNSS positioning error. Even though the DDE estimator was trained only on stationary point data, the proposed method improved the DGNSS positioning accuracy not only with stationary point but also with mobile rover. In addition, by comparing with the previous (detect and remove) approach, we confirmed the effectiveness of the DDE feedback approach.
ER -